© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 5876
    Prev
    Next
    INDEX
    Explanations

    code-related terms and constructs within a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     peri
    -0.15
    _interrupt
    -0.14
     Pent
    -0.14
     perc
    -0.14
     Hudson
    -0.14
    lsi
    -0.14
    graphics
    -0.14
    ACHI
    -0.14
    ypsy
    -0.14
    uri
    -0.13
    POSITIVE LOGITS
     protobuf
    0.43
     proto
    0.43
    Proto
    0.40
     prot
    0.39
    proto
    0.39
     Prot
    0.39
     Proto
    0.39
    .proto
    0.39
    protobuf
    0.38
    Prot
    0.37
    Activations Density 0.099%

    No Known Activations